ABSTRACT
Video summary is an active research field to help users to grasp a whole video's content for efficient browsing and editing. In this paper, we describe our THU-Intel rushes summarization system in TRECVID2008. In our approach, we first extract low-level audiovisual features and parse the video into shots, sub-shots and 1-second video clips. Then we remove junk video clips with color-bar, near uniform-color and clapboard frames etc. To select video clips with main objects and events, we evaluate each clip's representative score by multimodal features of color, edge, motion, and audio etc. Finally, we construct the rushes video summary by iteratively selecting the most representative video clips and removing similar ones. Extensive experiments are carried out on 40 testing rushes videos. Good results demonstrate the effectiveness of the proposed method.
- Alexander G. Hauptmann, Michael G. Christel, Wei-Hao Lin, et. al., Clever Clustering vs. Simple Speed-Up for Summarizing BBC Rushes, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007 Google ScholarDigital Library
- Anindya Sarkar, Emily Moxley, Stephen Mangiat, et al, Jim Kleban, Feature Fusion and Redundancy Pruning for Rush Video Summarization, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007. Google ScholarDigital Library
- Ba Tu Truong, Svetha Venkatesh, Generating Comprehensible Summaries of Rushes Sequences Based on Robust Feature Matching, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007 Google ScholarDigital Library
- Chen-Ming Pan, Yung-Yu Chuang, Winston H. Hsu, NTU TRECVID-2007 Fast Rushes Summarization System, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007. Google ScholarDigital Library
- Cong Li, Zhijian Ou, Wei hu, Tao Wang, Yimin Zhang, Caption-aided speech detection in videos, ICASSP 2008, pp141--144.Google Scholar
- D. Lowe. Object recognition from local scale-invariant features. In Proceedings of the 7th International Conference on Computer Vision (ICCV99), pages 1150--1157, Corfu, Greece, September 1999. Google ScholarDigital Library
- Feng Wang, Chong-Wah Ngo, Rushes Video Summarization by Object and Event Understanding, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007 Google ScholarDigital Library
- Li, Z., Schuster, G. M., Katsaggelos, A. K., Rate-Distortion Optimial Video Summary Generation, IEEE Trans. on Image Processing, 14(10), 2005. Google ScholarDigital Library
- M. Fischler and R. Bolles. Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography. Communications of the ACM, 24:381--395, 1981. Google ScholarDigital Library
- N. Dalai and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, pages 886--893, 2005. Google ScholarDigital Library
- P. Over, P., Smeaton, A.F. and Kelly, P., The TRECVID 2007 BBC Rushes Summarization Evaluation Pilot. In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007. Google ScholarDigital Library
- Park, J. I., Yagi, N., Enami, K., Aizawa, K., Hatori, M., Estimation of camera parameters from image sequence for model-based video coding, CirSysVideo(4), No. 3, June 1994, pp. 288--296.Google Scholar
- Paul Over and Alan F. Smeaton and George Awad, The TRECVID 2008 BBC rushes summarization evaluation, In Proc of the International Workshop on TRECVID Video Summarization(TVS '08), ACM Multimedia, 2008 Google ScholarDigital Library
- Tao Wang, Yue Gao, Jianguo Li, et al.m THU-ICRC at Rush Summarization of TRECVID 2007, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007. Google ScholarDigital Library
- Uchihashi, S., Foote, J., Girgensohn, A., Boreczky, J., Video Manga: Generating Semantically Meaningful Video Summaries, ACM Multimedia 1999 Google ScholarDigital Library
- Werner Bailer, Felix Lee, Georg Thallinger, Skimming Rushes Video Using Retake Detection, In Proc. of the TRECVID Workshop on Video Summarization (TVS'07), ACM Multimedia, 2007 Google ScholarDigital Library
- Yuan, J. H., Zheng, W. J., Chen, L., etc. Tsinghua University at TRECVID 2004: shot boundary detection and high-level feature extraction, In NIST workshop of TRECVID 2004.Google Scholar
Index Terms
- THU-intel at rushes summarization of TRECVID 2008
Recommendations
NTU TRECVID-2007 fast rushes summarization system
TVS '07: Proceedings of the international workshop on TRECVID video summarizationRushes are the raw materials used to produce a video. They often contain redundant and repetitive contents. Rushes summarization aims to provide a quick overview for a rushes video. As part of TRECVID 2007, NIST initiates a rushes summarization task. ...
Rushes video summarization using audio-visual information and sequence alignment
TVS '08: Proceedings of the 2nd ACM TRECVid Video Summarization WorkshopThis paper describes our system and methodologies for the BBC rushes video summarization task of TRECVID 2008. The procedure of the system is composed of three major steps: shot detection, irrelevant and repetitive subshot removal, and final summary ...
The trecvid 2008 BBC rushes summarization evaluation
TVS '08: Proceedings of the 2nd ACM TRECVid Video Summarization WorkshopThis paper describes an evaluation of automatic video summarization systems run on rushes from several BBC dramatic series. It was carried out under the auspices of the TREC Video Retrieval Evaluation (TRECVid) as a followup to the 2007 video ...
Comments